Tension control for multi-span web transport systems with roll inertia compensation using RBF neural network

Abstract

A roll-to-roll system which is a flexible multi-shaft web transport systems is very common in the industries such as paper,
metal processing, polymers or fabric and so on. However, web tension and speed controls of the roll-to-roll system are
difficult because of the nature of the system including multi-input multi-output, time variance, and nonlinearity. In this paper,
modeling and controling problems of the multispan roll to roll systerm are investigated. From the governing equations of the
web dynamics, a backstepping based controller with Neural RBF for web velocity and tension regulation is developed. The
neural network design is based on the Radial Basis Function network that estimates the uncertainty of roll inertia. Simulation
results show the effectiveness of the proposed approach.